OneCompression/mkdocs.yml at main · y-vectorfield/OneCompression · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
site_name: Fujitsu One Compression
site_description: Open-source Python library for post-training quantization of Large Language Models
site_url: https://FujitsuResearch.github.io/OneCompression/
repo_url: https://github.com/FujitsuResearch/OneCompression
repo_name: FujitsuResearch/OneCompression

theme:
  name: material
  palette:
    - media: "(prefers-color-scheme: light)"
      scheme: default
      primary: indigo
      accent: indigo
      toggle:
        icon: material/brightness-7
        name: Switch to dark mode
    - media: "(prefers-color-scheme: dark)"
      scheme: slate
      primary: indigo
      accent: indigo
      toggle:
        icon: material/brightness-4
        name: Switch to light mode
  features:
    - content.code.copy
    - content.code.annotate
    - navigation.tabs
    - navigation.sections
    - navigation.expand
    - navigation.top
    - search.suggest
    - search.highlight
    - toc.follow
  icon:
    repo: fontawesome/brands/github

plugins:
  - search
  - mkdocstrings:
      handlers:
        python:
          options:
            show_source: true
            show_root_heading: true
            show_root_full_path: false
            heading_level: 2
            members_order: source
            docstring_style: google
            show_signature_annotations: true
            separate_signature: true
            merge_init_into_class: true

markdown_extensions:
  - admonition
  - pymdownx.details
  - pymdownx.superfences
  - pymdownx.highlight:
      anchor_linenums: true
      line_spans: __span
      pygments_lang_class: true
  - pymdownx.inlinehilite
  - pymdownx.tabbed:
      alternate_style: true
  - pymdownx.arithmatex:
      generic: true
  - pymdownx.snippets:
      base_path: ["."]
  - pymdownx.emoji:
      emoji_index: !!python/name:material.extensions.emoji.twemoji
      emoji_generator: !!python/name:material.extensions.emoji.to_svg
  - attr_list
  - md_in_html
  - toc:
      permalink: true

extra_javascript:
  - javascripts/mathjax.js
  - https://unpkg.com/mathjax@3/es5/tex-mml-chtml.js

nav:
  - Home: index.md
  - Getting Started:
      - Installation: getting-started/installation.md
      - Quick Start: getting-started/quickstart.md
      - Tutorial Notebook: getting-started/tutorial-notebook.md
  - User Guide:
      - Basic Usage: user-guide/basic-usage.md
      - macOS / MPS: user-guide/mps.md
      - CLI: user-guide/cli.md
      - Configuration: user-guide/configuration.md
      - Pre-Process (Rotation): user-guide/pre-process.md
      - Post-Process (Global PTQ / Block-wise PTQ / LoRA SFT): user-guide/post-process.md
      - vLLM Inference: user-guide/vllm-inference.md
      - GPT-OSS: user-guide/gptoss.md
      - CPU Inference (llama.cpp / GGUF): user-guide/cpu-inference.md
      - GGUF Export: user-guide/gguf-export.md
      - Evaluation: user-guide/evaluation.md
      - Examples: user-guide/examples.md
  - Algorithms:
      - Overview: algorithms/overview.md
      - QEP (Quantization Error Propagation): algorithms/qep.md
      - LPCD (Layer-Projected Coordinate Descent): algorithms/lpcd.md
      - GPTQ: algorithms/gptq.md
      - DBF (Double Binary Factorization): algorithms/dbf.md
      - MDBF (Multi-Envelope Double Binary Factorization): algorithms/mdbf.md
      - RTN (Round-To-Nearest): algorithms/rtn.md
      - AutoBit (Mixed-Precision ILP): algorithms/autobit.md
      - JointQ (Joint Optimization): algorithms/jointq.md
  - API Reference:
      - api/index.md
      - Runner: api/runner.md
      - ModelConfig: api/model_config.md
      - CalibrationConfig: api/calibration_config.md
      - QEPConfig: api/qep_config.md
      - LPCDConfig: api/lpcd_config.md
      - Quantizers:
          - Base Classes: api/quantizers/base.md
          - AutoBit: api/quantizers/autobit.md
          - GPTQ: api/quantizers/gptq.md
          - DBF: api/quantizers/dbf.md
          - MDBF: api/quantizers/mdbf.md
          - RTN: api/quantizers/rtn.md
          - JointQ: api/quantizers/jointq.md
          - OneBit: api/quantizers/onebit.md
      - QuantizedModelLoader: api/quantized_model_loader.md
      - Pre-Process: api/pre_process.md
      - Post-Process: api/post_process.md
      - Evaluation: api/eval.md
      - Utilities: api/utilities.md
  - Contributing: contributing.md
  - Changelog: changelog.md